In [1]:
# %matplotlib inline
import matplotlib.pyplot as plt
import pandas as pd
import plotly.graph_objects as go
from plotly.offline import init_notebook_mode, iplot
In [2]:
plt.style.use('seaborn-white')
In [3]:
dt = pd.read_csv('./netflix-shows/netflix_titles.csv')
In [4]:
dt
Out[4]:
In [5]:
# addding extra feature
dt['date_added'] = pd.to_datetime(dt['date_added'])
dt['year_added'] = dt['date_added'].dt.year
dt['month_added'] = dt['date_added'].dt.month
In [6]:
dt['season_count'] = dt.apply(lambda x : x['duration'].split(" ")[0] if "Season" in x['duration'] else "",axis = 1)
dt['duration'] = dt.apply(lambda x : x['duration'].split(" ")[0] if "Season" not in x['duration'] else "",axis = 1)
In [7]:
dt.head()
Out[7]:
In [8]:
col = "type"
grouped = dt[col].value_counts().reset_index()
grouped = grouped.rename(columns = {col : "Count", "index" : col})
In [9]:
grouped.head()
Out[9]:
In [10]:
fig = plt.figure(figsize=(5,5))
explode = [0.0,0.05]
plt.pie(grouped['Count'] ,labels= ['Movie','TV Show'],explode = explode,shadow = False,autopct='%1.0f%%',startangle = 20,colors = ['#48BFA0','#F9ED94','#E6543B'])
plt.title('Pie Chart')
plt.tight_layout()
plt.show()
In [11]:
dt1 = dt[dt['type'] == 'TV Show']
dt2 = dt[dt['type'] == 'Movie']
col = 'year_added'
In [12]:
vc1 = dt1[col].value_counts().reset_index()
vc1 = vc1.rename(columns = {col:'count','index':col})
vc1['percent'] = vc1['count'].apply(lambda x: 100 * x / sum(vc1['count']))
vc1 = vc1.sort_values(col)
In [13]:
vc1.head()
Out[13]:
In [14]:
vc2 = dt2[col].value_counts().reset_index()
vc2 = vc2.rename(columns = {col:'count','index':col})
vc2['percent'] = vc2['count'].apply(lambda x: 100 * x / sum(vc2['count']))
vc2 = vc2.sort_values(col)
In [15]:
vc2.head()
Out[15]:
In [16]:
fig=plt.figure(figsize=(14, 8), dpi= 300)
plt.plot(vc1[col],vc1['count'],label='TV Show',marker='o',color='#48BFA0')
plt.plot(vc2[col],vc2['count'],label='Movie',marker='o',color='#E6543B')
plt.title('Content added over the years')
plt.xlabel('Year')
plt.ylabel('Count')
plt.legend()
plt.grid(True)
plt.tight_layout()
In [17]:
col = 'release_year'
vc1 = dt1[col].value_counts().reset_index()
vc1 = vc1.rename(columns = {col:'count','index':col})
vc1['percent'] = vc1['count'].apply(lambda x: 100 * x / sum(vc1['count']))
vc1 = vc1.sort_values(col)
vc2 = dt2[col].value_counts().reset_index()
vc2 = vc2.rename(columns = {col:'count','index':col})
vc2['percent'] = vc2['count'].apply(lambda x: 100 * x / sum(vc2['count']))
vc2 = vc2.sort_values(col)
In [18]:
fig=plt.figure(figsize=(14, 8), dpi= 300)
width = 0.3
plt.bar(vc1[col] + width/1.5,vc1['count'],label='TV Show',color='#48BFA0', width = width)
plt.bar(vc2[col] - width/1.5,vc2['count'],label='Movie',color='#E6543B', width = width)
plt.legend()
plt.title('Content released over the years')
plt.xlabel('Year')
plt.ylabel('Count')
plt.grid(True)
plt.tight_layout()
In [19]:
trace1 = go.Bar(x=vc1[col],y=vc1['count'],name='TV Shows',marker = dict(color='#48BFA0'))
trace2 = go.Bar(x=vc2[col],y=vc2['count'],name='Movies',marker = dict(color='#E6543B'))
data = [trace1,trace2]
layout = go.Layout(title = "Content released over the years",legend=dict(x=0.1,y=1.1,orientation='h'))
fig = go.Figure(data,layout=layout)
fig.show()
In [20]:
col = 'month_added'
vc1 = dt1[col].value_counts().reset_index()
vc1 = vc1.rename(columns = {col:'count','index':col})
vc1['percent'] = vc1['count'].apply(lambda x: 100 * x / sum(vc1['count']))
vc1 = vc1.sort_values(col)
In [21]:
trace1 = go.Bar(x=vc1[col],y=vc1['count'],name='TV Shows',marker = dict(color = '#48BFA0'), width = 0.3)
data = [trace1]
layout = go.Layout(title = 'Content added by Months',legend=dict(x=0.1,y=1.1,orientation='h'))
fig = go.Figure(data,layout = layout)
fig.show()
In [22]:
print('Some Oldest movies on Netflix')
small = dt.sort_values('release_year',ascending = True)
small = small[small['duration']!='']
small[['title','release_year']][:15]
Out[22]:
In [23]:
print('Some Oldest movies on Netflix')
small = dt.sort_values('release_year',ascending = True)
small = small[small['season_count']!='']
small[['title','release_year']][:15]
Out[23]:
In [24]:
country_codes = {'afghanistan': 'AFG',
'albania': 'ALB',
'algeria': 'DZA',
'american samoa': 'ASM',
'andorra': 'AND',
'angola': 'AGO',
'anguilla': 'AIA',
'antigua and barbuda': 'ATG',
'argentina': 'ARG',
'armenia': 'ARM',
'aruba': 'ABW',
'australia': 'AUS',
'austria': 'AUT',
'azerbaijan': 'AZE',
'bahamas': 'BHM',
'bahrain': 'BHR',
'bangladesh': 'BGD',
'barbados': 'BRB',
'belarus': 'BLR',
'belgium': 'BEL',
'belize': 'BLZ',
'benin': 'BEN',
'bermuda': 'BMU',
'bhutan': 'BTN',
'bolivia': 'BOL',
'bosnia and herzegovina': 'BIH',
'botswana': 'BWA',
'brazil': 'BRA',
'british virgin islands': 'VGB',
'brunei': 'BRN',
'bulgaria': 'BGR',
'burkina faso': 'BFA',
'burma': 'MMR',
'burundi': 'BDI',
'cabo verde': 'CPV',
'cambodia': 'KHM',
'cameroon': 'CMR',
'canada': 'CAN',
'cayman islands': 'CYM',
'central african republic': 'CAF',
'chad': 'TCD',
'chile': 'CHL',
'china': 'CHN',
'colombia': 'COL',
'comoros': 'COM',
'congo democratic': 'COD',
'Congo republic': 'COG',
'cook islands': 'COK',
'costa rica': 'CRI',
"cote d'ivoire": 'CIV',
'croatia': 'HRV',
'cuba': 'CUB',
'curacao': 'CUW',
'cyprus': 'CYP',
'czech republic': 'CZE',
'denmark': 'DNK',
'djibouti': 'DJI',
'dominica': 'DMA',
'dominican republic': 'DOM',
'ecuador': 'ECU',
'egypt': 'EGY',
'el salvador': 'SLV',
'equatorial guinea': 'GNQ',
'eritrea': 'ERI',
'estonia': 'EST',
'ethiopia': 'ETH',
'falkland islands': 'FLK',
'faroe islands': 'FRO',
'fiji': 'FJI',
'finland': 'FIN',
'france': 'FRA',
'french polynesia': 'PYF',
'gabon': 'GAB',
'gambia, the': 'GMB',
'georgia': 'GEO',
'germany': 'DEU',
'ghana': 'GHA',
'gibraltar': 'GIB',
'greece': 'GRC',
'greenland': 'GRL',
'grenada': 'GRD',
'guam': 'GUM',
'guatemala': 'GTM',
'guernsey': 'GGY',
'guinea-bissau': 'GNB',
'guinea': 'GIN',
'guyana': 'GUY',
'haiti': 'HTI',
'honduras': 'HND',
'hong kong': 'HKG',
'hungary': 'HUN',
'iceland': 'ISL',
'india': 'IND',
'indonesia': 'IDN',
'iran': 'IRN',
'iraq': 'IRQ',
'ireland': 'IRL',
'isle of man': 'IMN',
'israel': 'ISR',
'italy': 'ITA',
'jamaica': 'JAM',
'japan': 'JPN',
'jersey': 'JEY',
'jordan': 'JOR',
'kazakhstan': 'KAZ',
'kenya': 'KEN',
'kiribati': 'KIR',
'north korea': 'PRK',
'south korea': 'KOR',
'kosovo': 'KSV',
'kuwait': 'KWT',
'kyrgyzstan': 'KGZ',
'laos': 'LAO',
'latvia': 'LVA',
'lebanon': 'LBN',
'lesotho': 'LSO',
'liberia': 'LBR',
'libya': 'LBY',
'liechtenstein': 'LIE',
'lithuania': 'LTU',
'luxembourg': 'LUX',
'macau': 'MAC',
'macedonia': 'MKD',
'madagascar': 'MDG',
'malawi': 'MWI',
'malaysia': 'MYS',
'maldives': 'MDV',
'mali': 'MLI',
'malta': 'MLT',
'marshall islands': 'MHL',
'mauritania': 'MRT',
'mauritius': 'MUS',
'mexico': 'MEX',
'micronesia': 'FSM',
'moldova': 'MDA',
'monaco': 'MCO',
'mongolia': 'MNG',
'montenegro': 'MNE',
'morocco': 'MAR',
'mozambique': 'MOZ',
'namibia': 'NAM',
'nepal': 'NPL',
'netherlands': 'NLD',
'new caledonia': 'NCL',
'new zealand': 'NZL',
'nicaragua': 'NIC',
'nigeria': 'NGA',
'niger': 'NER',
'niue': 'NIU',
'northern mariana islands': 'MNP',
'norway': 'NOR',
'oman': 'OMN',
'pakistan': 'PAK',
'palau': 'PLW',
'panama': 'PAN',
'papua new guinea': 'PNG',
'paraguay': 'PRY',
'peru': 'PER',
'philippines': 'PHL',
'poland': 'POL',
'portugal': 'PRT',
'puerto rico': 'PRI',
'qatar': 'QAT',
'romania': 'ROU',
'russia': 'RUS',
'rwanda': 'RWA',
'saint kitts and nevis': 'KNA',
'saint lucia': 'LCA',
'saint martin': 'MAF',
'saint pierre and miquelon': 'SPM',
'saint vincent and the grenadines': 'VCT',
'samoa': 'WSM',
'san marino': 'SMR',
'sao tome and principe': 'STP',
'saudi arabia': 'SAU',
'senegal': 'SEN',
'serbia': 'SRB',
'seychelles': 'SYC',
'sierra leone': 'SLE',
'singapore': 'SGP',
'sint maarten': 'SXM',
'slovakia': 'SVK',
'slovenia': 'SVN',
'solomon islands': 'SLB',
'somalia': 'SOM',
'south africa': 'ZAF',
'south sudan': 'SSD',
'spain': 'ESP',
'sri lanka': 'LKA',
'sudan': 'SDN',
'suriname': 'SUR',
'swaziland': 'SWZ',
'sweden': 'SWE',
'switzerland': 'CHE',
'syria': 'SYR',
'taiwan': 'TWN',
'tajikistan': 'TJK',
'tanzania': 'TZA',
'thailand': 'THA',
'timor-leste': 'TLS',
'togo': 'TGO',
'tonga': 'TON',
'trinidad and tobago': 'TTO',
'tunisia': 'TUN',
'turkey': 'TUR',
'turkmenistan': 'TKM',
'tuvalu': 'TUV',
'uganda': 'UGA',
'ukraine': 'UKR',
'united arab emirates': 'ARE',
'united kingdom': 'GBR',
'united states': 'USA',
'uruguay': 'URY',
'uzbekistan': 'UZB',
'vanuatu': 'VUT',
'venezuela': 'VEN',
'vietnam': 'VNM',
'virgin islands': 'VGB',
'west bank': 'WBG',
'yemen': 'YEM',
'zambia': 'ZMB',
'zimbabwe': 'ZWE'}
In [25]:
## countries
from collections import Counter
colorscale = ["#f7fbff", "#ebf3fb", "#deebf7", "#d2e3f3", "#c6dbef", "#b3d2e9", "#9ecae1",
"#85bcdb", "#6baed6", "#57a0ce", "#4292c6", "#3082be", "#2171b5", "#1361a9",
"#08519c", "#0b4083", "#08306b"
]
def geoplot(ddf):
country_with_code, country = {}, {}
shows_countries = ", ".join(ddf['country'].dropna()).split(", ")
for c,v in dict(Counter(shows_countries)).items():
code = ""
if c.lower() in country_codes:
code = country_codes[c.lower()]
country_with_code[code] = v
country[c] = v
data = [dict(
type = 'choropleth',
locations = list(country_with_code.keys()),
z = list(country_with_code.values()),
colorscale = [[0,"#000000"],[0.65,"#007575"],[0.75,"#00A3A3"],[0.8,"#00D1D1"],[0.9,"#00FFFF"],[0.95,"#8AFFFF"],[1,"#FFFFFF"]],
autocolorscale = False,
reversescale = True,
marker = dict(
line = dict (
color = 'gray',
width = 0.5
) ),
colorbar = dict(
autotick = False,
title = ''),
) ]
layout = dict(
title = '',
geo = dict(
showframe = False,
showcoastlines = False,
projection = dict(
type = 'Mercator'
)
)
)
fig = dict( data=data, layout=layout )
iplot( fig, validate=False, filename='d3-world-map' )
return country
country_vals = geoplot(dt)
tabs = Counter(country_vals).most_common(25)
labels = [_[0] for _ in tabs][::-1]
values = [_[1] for _ in tabs][::-1]
trace1 = go.Bar(y=labels, x=values, orientation="h", name="", marker=dict(color="#48BFA0"))
data = [trace1]
layout = go.Layout(title="Countries with most content", height=700, legend=dict(x=0.1, y=1.1, orientation="h"))
fig = go.Figure(data, layout=layout)
fig.show()
In [26]:
import plotly.figure_factory as ff
x1 = dt2['duration'].fillna(0.0).astype(float)
fig = ff.create_distplot([x1],['a'],bin_size = 0.7,curve_type = 'normal', colors = ['#48BFA0'])
fig.update_layout(title_text = 'Distplot with Normal Distribution')
fig.show()
In [27]:
dt1.head()
Out[27]:
In [28]:
col = 'season_count'
vc1 = dt1[col].value_counts().reset_index()
vc1 = vc1.rename(columns = {col:'count','index':col})
vc1['percent'] = vc1['count'].apply(lambda x: 100 * x / sum(vc1['count']))
vc1 = vc1.sort_values(col)
trace1 = go.Bar(x = vc1[col], y = vc1['count'],name='TV Shows',marker = dict(color = '#48BFA0'))
data = [trace1]
layout = go.Layout(title = 'Seasons',legend=dict(x=0.1,y=1.1,orientation = 'h'))
fig = go.Figure(data,layout = layout)
fig.show()
In [29]:
col = 'rating'
vc1 = dt1[col].value_counts().reset_index()
vc1 = vc1.rename(columns = {col:'count','index':col})
vc1 = vc1.sort_values('count')
vc2 = dt2[col].value_counts().reset_index()
vc2 = vc2.rename(columns = {col:'count','index':col})
vc2 = vc2.sort_values('count')
In [30]:
trace1 = go.Bar(x = vc1[col],y = vc1['count'],name = 'TV Shows', marker = dict(color = '#48BFA0'))
trace2 = go.Bar(x = vc2[col],y = vc2['count'],name = 'Movies' , marker = dict(color = '#F9ED94'))
data = [trace1,trace2]
layout = go.Layout(title = 'Ratings' , legend= dict(x = 0.1, y= 1.1, orientation = 'h'))
plt = go.Figure(data,layout = layout)
plt.show()
In [31]:
col = "listed_in"
categories = ", ".join(dt['listed_in']).split(", ")
counter_list = Counter(categories).most_common(50)
labels = [_[0] for _ in counter_list][::-1]
values = [_[1] for _ in counter_list][::-1]
trace1 = go.Bar(y=labels, x=values, orientation="h", name="TV Shows", marker=dict(color="#48BFA0"),width = 0.5)
data = [trace1]
layout = go.Layout(title="Content added over the years", legend=dict(x=0.1, y=1.1, orientation="h"))
fig = go.Figure(data, layout=layout)
fig.show()
In [39]:
def country_trace(country, flag = "movie"):
dt["from_us"] = dt['country'].fillna("").apply(lambda x : 1 if country.lower() in x.lower() else 0)
small = dt[dt["from_us"] == 1]
if flag == "movie":
small = small[small["duration"] != ""]
else:
small = small[small["season_count"] != ""]
cast = ", ".join(small['cast'].fillna("")).split(", ")
tags = Counter(cast).most_common(25)
tags = [_ for _ in tags if "" != _[0]]
labels, values = [_[0]+" " for _ in tags], [_[1] for _ in tags]
trace = go.Bar(y=labels[::-1], x=values[::-1], orientation="h", name="", marker=dict(color="#48BFA0"))
return trace
from plotly.subplots import make_subplots
traces = []
titles = ["United States", "","India","", "United Kingdom", "Canada","", "Spain","", "Japan"]
for title in titles:
if title != "":
traces.append(country_trace(title))
fig = make_subplots(rows=2, cols=5, subplot_titles=titles)
fig.add_trace(traces[0], 1,1)
fig.add_trace(traces[1], 1,3)
fig.add_trace(traces[2], 1,5)
fig.add_trace(traces[3], 2,1)
fig.add_trace(traces[4], 2,3)
fig.add_trace(traces[5], 2,5)
fig.update_layout(height=1200, showlegend=False)
fig.show()
In [40]:
traces = []
titles = ["United States", "","India","", "United Kingdom", "Canada","", "Spain","", "Japan"]
for title in titles:
if title != "":
traces.append(country_trace(title,flag = 'TV Shows'))
fig = make_subplots(rows=2, cols=5, subplot_titles=titles)
fig.add_trace(traces[0], 1,1)
fig.add_trace(traces[1], 1,3)
fig.add_trace(traces[2], 1,5)
fig.add_trace(traces[3], 2,1)
fig.add_trace(traces[4], 2,3)
fig.add_trace(traces[5], 2,5)
fig.update_layout(height=1200, showlegend=False)
fig.show()